Tissue Cross-Section and Pen Marking Segmentation in Whole Slide Images

TL;DR

This paper tackles robust tissue segmentation in whole slide images and the removal of pen markings to prevent bias in downstream analyses, while also enabling separation of multiple tissue cross-sections on a single slide. It introduces a CNN that predicts tissue, pen markings, and distance-to-centroid maps, coupled with a centroid-based post-processing pipeline that uses a 2D histogram to separate cross-sections. On a dataset of 200 WSIs with an independent test set, the method achieves a tissue Dice of 0.981 and a pen marking Dice of 0.912, with precise cross-section separation evidenced by a mean cross-section count error of 0.075. The approach is released as SlideSegmenter, demonstrating robust preprocessing performance and potential for generalization to other tissue types and staining schemes.

Abstract

Tissue segmentation is a routine preprocessing step to reduce the computational cost of whole slide image (WSI) analysis by excluding background regions. Traditional image processing techniques are commonly used for tissue segmentation, but often require manual adjustments to parameter values for atypical cases, fail to exclude all slide and scanning artifacts from the background, and are unable to segment adipose tissue. Pen marking artifacts in particular can be a potential source of bias for subsequent analyses if not removed. In addition, several applications require the separation of individual cross-sections, which can be challenging due to tissue fragmentation and adjacent positioning. To address these problems, we develop a convolutional neural network for tissue and pen marking segmentation using a dataset of 200 H&E stained WSIs. For separating tissue cross-sections, we propose a novel post-processing method based on clustering predicted centroid locations of the cross-sections in a 2D histogram. On an independent test set, the model achieved a mean Dice score of 0.981$\pm$0.033 for tissue segmentation and a mean Dice score of 0.912$\pm$0.090 for pen marking segmentation. The mean absolute difference between the number of annotated and separated cross-sections was 0.075$\pm$0.350. Our results demonstrate that the proposed model can accurately segment H&E stained tissue cross-sections and pen markings in WSIs while being robust to many common slide and scanning artifacts. The model with trained model parameters and post-processing method are made publicly available as a Python package called SlideSegmenter.

Figures (3)

• Figure 1: (a) Examples of slide and scanning artifacts cropped from WSIs (top row) and corresponding segmentation results using MorphologicalMasker from the TIAToolboxpocock2022tiatoolbox (version 1.5.1) with default parameter values (bottom row). (b) Example of two tissue cross-sections with adjacent positioning and fragmentation.
• Figure 2: Overview of the proposed method for tissue cross-section and pen marking segmentation.
• Figure 3: Results for four WSIs from the test set. The segmentation results show true positives in white, true negatives in black, false positives in red, and false negatives in blue. The rightmost column shows the separated cross-sections indicated by different colors with the predicted centroid locations as white dots.